This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a given RNN using active automata learning. This model may then be analyzed using model checking as verification technique. The term property-directed reflects the idea that our procedure is guided and controlled by the given property rather than performing the two steps separately. We show that this not only allows us to discover small counterexamples fast, but also to generalize them by pumping towards faulty flows hinting at the underlying error in the RNN.

中文翻译：

---

循环神经网络的属性导向验证

本文提出了一种以属性为导向的方法来验证循环神经网络 (RNN)。为此，我们使用主动自动机学习从给定的 RNN 中学习了一个确定性有限自动机作为代理模型。然后可以使用模型检查作为验证技术来分析该模型。术语属性导向反映了这样一种想法，即我们的程序由给定的属性引导和控制，而不是分别执行两个步骤。我们表明，这不仅使我们能够快速发现小的反例，而且还可以通过向暗示 RNN 中潜在错误的错误流泵送来概括它们。